Power system planning method for renewable energy sources

Abstract

The invention discloses a renewable energy source-oriented power system planning method. The method comprises the following steps of S1, collecting load data of a power system; s2, according to the historical renewable resource power generation power, the historical meteorological data and the predicted meteorological data, predicting renewable resource power generation power within a preset time range; s3, predicting a power load demand in a preset future time range by adopting LSTM according to the collected load data and historical load data; s4, according to the predicted power generation power, the predicted power load demand, a preset constraint condition and a preset optimization target, a power system planning model is constructed, and the optimization target comprises the minimum power generation cost and the maximum renewable energy utilization rate; and S5, solving the power system planning model by adopting a genetic algorithm to obtain an optimal power system planning scheme. Through the optimal power system planning scheme, the power generation cost is reduced, and the utilization rate of renewable energy sources is improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a power system planning method oriented to renewable energy. Background Art

[0002] The use of renewable energy sources such as solar energy and wind energy to replace traditional energy has become an important trend in global energy development. However, how to rationally plan and optimize the access of renewable energy in the power system remains a difficult problem. Traditional power system planning methods mainly rely on fossil fuel energy, with a low utilization rate of renewable energy, making it difficult to meet the needs of low-carbon and environmental protection. Summary of the Invention

[0003] In view of the shortcomings of the existing technology, the present invention provides a power system planning method for renewable energy.

[0004] The method for planning a power system for renewable energy provided by the present invention comprises the following steps:

[0005] S1: Collect load data of the power system;

[0006] S2: Obtaining historical renewable resource power generation, historical meteorological data, and meteorological data predicted by a weather forecast, and predicting renewable resource power generation within a preset time range based on the historical renewable resource power generation, the historical meteorological data, and the predicted meteorological data;

[0007] S3: Obtain historical load data, and use LSTM to predict the power load demand within a preset future time range based on the collected load data and the historical load data;

[0008] S4: constructing a power system planning model based on the predicted power generation, the predicted power load demand, preset constraints, and preset optimization objectives, wherein the optimization objectives include minimizing power generation costs and maximizing renewable energy utilization;

[0009] S5: Use a genetic algorithm to solve the power system planning model and obtain the optimal power system planning scheme, including the output ratio of the generator sets, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment.

[0010] In a preferred embodiment, the step S2 is specifically as follows:

[0011] Cleaning the historical renewable resource power generation, the historical meteorological data, and the predicted meteorological data, including processing missing values, outliers, and noise data;

[0012] Normalizing or standardizing the historical meteorological data and the predicted meteorological data;

[0013] Aligning the historical renewable resource power generation, the historical meteorological data, and the predicted meteorological data in time series to form a unified data set;

[0014] Extract key features from historical and forecasted meteorological data, including wind direction, wind speed, and solar radiation;

[0015] Train a random forest model based on key features of historical meteorological data and historical renewable energy generation power;

[0016] The pre-processed forecasted meteorological data is input into the random forest model to predict the renewable energy power generation in a preset time period.

[0017] Preferably, in step S3, specifically,

[0018] Clean and normalize the load data and historical load data collected in step S1, remove outliers and missing values, and normalize the data to the same scale;

[0019] Extract features from the preprocessed data, including time features and historical load features;

[0020] Constructing an LSTM neural network model, wherein the LSTM neural network model includes an input layer, a hidden layer, and an output layer, wherein the hidden layer is composed of multiple LSTM units;

[0021] Use historical load data to train the LSTM neural network model, optimize the LSTM neural network model parameters through the back propagation algorithm, and minimize the prediction error;

[0022] The LSTM neural network model trained with real-time collected load data is used to predict the power load demand within a preset future time range.

[0023] Preferably, in step S4, specifically,

[0024] Defining decision variables of the power system planning model, wherein the decision variables include the output of the generator set, the charge and discharge power of the energy storage system, and the utilization rate of the renewable energy power generation equipment;

[0025] Presetting an optimization goal, wherein the optimization goal includes minimizing power generation cost and maximizing renewable energy utilization;

[0026] Preset constraints, wherein the constraints include power balance constraints, grid security constraints, and energy storage system constraints;

[0027] The predicted power generation power, predicted power load demand, optimization objectives and constraints are integrated to construct a power system planning model.

[0028] Preferably, the step S5 specifically includes the following sub-steps:

[0029] S51: Convert the power system planning model into an optimization problem, and define an objective function and constraints. The objective function includes minimizing power generation cost and maximizing renewable energy utilization. The constraints include power balance constraints, grid security constraints, and energy storage system constraints.

[0030] S52: Initializing a population of a genetic algorithm, where the population consists of a plurality of individuals, each of which represents a possible power system planning scheme, including the output ratio of the generator sets, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment;

[0031] S53: Calculating the fitness value of each individual in the population, where the fitness value is calculated according to the objective function;

[0032] S54: Generate a new generation population through selection, crossover and mutation operations, wherein the selection operation selects excellent individuals based on fitness values, the crossover operation generates new individuals by exchanging individual genes, and the mutation operation introduces diversity by randomly changing individual genes;

[0033] S55: Repeat the sub-steps S53 and S54 until a preset number of iterations is reached;

[0034] S56: Select the individual with the best fitness value from the final population as the optimal power system planning scheme, including the output ratio of the generator sets, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment;

[0035] S57: Verify the optimal power system planning scheme to see whether it meets preset constraints. If so, output the optimal power system planning scheme.

[0036] The present invention discloses a power system planning method for renewable energy, which has the following beneficial effects:

[0037] The power system planning method for renewable energy provided by the present invention can estimate the power generation power of renewable energy in the future time range, which helps to better arrange the scheduling of renewable energy and avoid grid instability caused by power generation power fluctuations. By obtaining the optimal utilization rate of renewable energy power generation equipment, the proportion of renewable energy in the entire power system is increased. By estimating the power load demand in the future time range, it helps the power system to make scheduling preparations in advance and reasonably arrange the output plan of the generator set to avoid grid overload or power shortage caused by load fluctuations. By optimizing the charging and discharging strategy of the energy storage system, it can effectively adjust the supply and demand balance of the power system when the power generation power of renewable energy fluctuates, thereby improving the stability and reliability of the power system. By minimizing the power generation cost as one of the optimization goals, it can find the lowest cost power generation plan under the premise of meeting the power load demand and renewable energy utilization rate. Based on the predicted power generation power and power load demand, the output plan of the generator set is optimized to avoid unnecessary power generation equipment operation, thereby reducing power generation costs. By collecting and analyzing real-time data and combining historical data for prediction and optimization, it can make the power system better adapt to different operating scenarios, such as seasonal changes and changes in meteorological conditions. By accurately predicting power generation and load demand and optimizing energy storage system strategies, we can effectively solve problems such as large fluctuations and strong intermittency in renewable energy power generation, and improve the power system's ability to access renewable energy. By optimizing the output plan of the generator set and the charging and discharging strategy of the energy storage system, we can reduce power generation costs, improve the utilization rate of renewable energy, and reduce dependence on traditional fossil energy while meeting power load demand, thereby reducing the carbon emissions of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0039] Figure 1 A methodological flow chart for a renewable energy-oriented power system planning approach;

[0040] Figure 2 This is a flowchart of the sub-steps in step S5 of the method for power system planning for renewable energy sources. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0042] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0043] refer to Figure 1 The power system planning method for renewable energy provided by the present invention includes the following:

[0044] S1: Collect load data of the power system;

[0045] S2: Obtaining historical renewable resource power generation, historical meteorological data, and meteorological data predicted by a weather forecast, and predicting renewable resource power generation within a preset time range based on the historical renewable resource power generation, the historical meteorological data, and the predicted meteorological data;

[0046] S3: Obtain historical load data, and use LSTM to predict the power load demand within a preset future time range based on the collected load data and the historical load data;

[0047] S4: constructing a power system planning model based on the predicted power generation, the predicted power load demand, preset constraints, and preset optimization objectives, wherein the optimization objectives include minimizing power generation costs and maximizing renewable energy utilization;

[0048] S5: Use a genetic algorithm to solve the power system planning model and obtain the optimal power system planning scheme, including the output ratio of the generator sets, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment.

[0049] The power system planning method for renewable energy provided by the present invention can estimate the power generation power of renewable energy in the future time range, which helps to better arrange the scheduling of renewable energy and avoid grid instability caused by power generation power fluctuations. By obtaining the optimal utilization rate of renewable energy power generation equipment, the proportion of renewable energy in the entire power system is increased. By estimating the power load demand in the future time range, it helps the power system to make scheduling preparations in advance and reasonably arrange the output plan of the generator set to avoid grid overload or power shortage caused by load fluctuations. By optimizing the charging and discharging strategy of the energy storage system, it can effectively adjust the supply and demand balance of the power system when the power generation power of renewable energy fluctuates, thereby improving the stability and reliability of the power system. By minimizing the power generation cost as one of the optimization goals, it can find the lowest cost power generation plan under the premise of meeting the power load demand and renewable energy utilization rate. Based on the predicted power generation power and power load demand, the output plan of the generator set is optimized to avoid unnecessary power generation equipment operation, thereby reducing power generation costs. By collecting and analyzing real-time data and combining historical data for prediction and optimization, it can make the power system better adapt to different operating scenarios, such as seasonal changes and changes in meteorological conditions. By accurately predicting power generation and load demand and optimizing energy storage system strategies, we can effectively solve problems such as large fluctuations and strong intermittency in renewable energy power generation, and improve the power system's ability to access renewable energy. By optimizing the output plan of the generator set and the charging and discharging strategy of the energy storage system, we can reduce power generation costs, improve the utilization rate of renewable energy, and reduce dependence on traditional fossil energy while meeting power load demand, thereby reducing the carbon emissions of the power system.

[0050] In a preferred embodiment, in step S2, specifically,

[0051] Clean historical renewable energy power generation, historical meteorological data, and forecasted meteorological data, including processing missing values, outliers, and noise data;

[0052] Normalize or standardize historical meteorological data and forecast meteorological data;

[0053] Align historical renewable energy generation power, historical meteorological data, and forecasted meteorological data in time series to form a unified data set;

[0054] Extract key features from historical and forecasted meteorological data, including wind direction, wind speed, and solar radiation;

[0055] Train a random forest model based on key features of historical meteorological data and historical renewable energy generation power;

[0056] The pre-processed forecasted meteorological data is input into the random forest model to predict the renewable energy power generation in a preset time period.

[0057] In a preferred embodiment, in step S3, specifically,

[0058] Clean and normalize the load data and historical load data collected in step S1, remove outliers and missing values, and normalize the data to the same scale;

[0059] Extract features from the preprocessed data, including time features such as hour, week, month, etc., and historical load features;

[0060] Build an LSTM neural network model. The LSTM neural network model includes an input layer, a hidden layer, and an output layer. The hidden layer consists of multiple LSTM units.

[0061] Use historical load data to train the LSTM neural network model, optimize the LSTM neural network model parameters through the back propagation algorithm, and minimize the prediction error;

[0062] The LSTM neural network model trained with real-time collected load data is used to predict the power load demand within a preset future time range.

[0063] In a preferred embodiment, in step S4, specifically,

[0064] Define the decision variables of the power system planning model, including the output of the generator set, the charge and discharge power of the energy storage system, and the utilization rate of renewable energy power generation equipment;

[0065] Preset optimization objectives, including minimizing power generation costs and maximizing renewable energy utilization;

[0066] Preset constraints, including power balance constraints, grid security constraints, and energy storage system constraints;

[0067] The predicted power generation power, predicted power load demand, optimization objectives and constraints are integrated to construct a power system planning model.

[0068] refer to Figure 2 In a preferred embodiment, step S5 specifically includes the following sub-steps:

[0069] S51: Convert the power system planning model into an optimization problem and define the objective function and constraints. The objective function includes minimizing the power generation cost and maximizing the utilization of renewable energy. The constraints include power balance constraints, grid security constraints, and energy storage system constraints.

[0070] Among them, the power generation cost includes the cost of traditional energy power generation, the cost of renewable energy power generation and the operating cost of the energy storage system;

[0071] Among them, the objective function of minimizing the power generation cost is specifically:

[0072]

[0073] Among them, C total is the total power generation cost;

[0074] T is the time range such as 24 hours, 365 days, etc.;

[0075] N conv is the number of traditional generator sets;

[0076] C conv,i is the unit power generation cost of the i-th traditional generator set;

[0077] P conv,i(t) is the power generation of the i-th traditional generator set at time t;

[0078] N ren The number of renewable energy generating units;

[0079] C ren,j is the unit power generation cost of the j-th renewable energy generator;

[0080] P ren,j(t) is the power generation of the jth renewable energy generator at time t;

[0081] C storage is the unit operating cost of the energy storage system;

[0082] P storage(t) is the charge and discharge power of the energy storage system at time t, where a positive value indicates discharge and a negative value indicates charge.

[0083] The objective function for maximizing the utilization rate of renewable energy is:

[0084]

[0085] Among them, U ren : Renewable energy utilization rate; other parameters are consistent with the definitions in the power generation cost function.

[0086] The two objective functions are weighted summed to integrate the two objective functions into a single objective function:

[0087] Minimize F=w1·C total +w2·(1-U ren ),

[0088] w1 and w2 are weight coefficients.

[0089] The power balance constraint is to balance the power generation power with the load demand and the charging and discharging power of the energy storage system; the grid safety constraint includes line transmission capacity limitations, voltage stability and frequency stability requirements; the energy storage system constraint includes energy storage capacity limitations, charging and discharging efficiency limitations, and charging and discharging power limitations; the above constraints can be adjusted according to the specific circumstances of use.

[0090] S52: Initialize the population of the genetic algorithm. The population consists of multiple individuals, each of which represents a possible power system planning scheme, including the output ratio of the generator sets, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment.

[0091] S53: Calculate the fitness value of each individual in the population, where the fitness value is calculated based on the single objective function integrated in step S4;

[0092] S54: Generate a new generation of population through selection, crossover and mutation operations. The selection operation selects individuals based on their fitness values, the crossover operation generates new individuals by exchanging individual genes, and the mutation operation introduces diversity by randomly changing individual genes.

[0093] S55: Repeat sub-steps S53 and S54 until the preset number of iterations is reached;

[0094] S56: Select the individual with the highest fitness value from the final population as the optimal power system planning scheme, including the output ratio of the generator set, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment; among which, the charging and discharging strategy of the energy storage system is to charge during low load and discharge during peak load.

[0095] S57: Verify the optimal power system planning scheme to see whether it satisfies preset constraints. If so, output the optimal power system planning scheme.

Claims

1. A power system planning method for renewable energy, characterized in that: The steps include: S1: Collect load data of the power system; S2: Obtaining historical renewable resource power generation, historical meteorological data, and meteorological data predicted by a weather forecast, and predicting renewable resource power generation within a preset time range based on the historical renewable resource power generation, the historical meteorological data, and the predicted meteorological data; S3: Obtain historical load data, and use LSTM to predict the power load demand within a preset future time range based on the collected load data and the historical load data; S4: constructing a power system planning model based on the predicted power generation, the predicted power load demand, preset constraints, and preset optimization objectives, wherein the optimization objectives include minimizing power generation costs and maximizing renewable energy utilization; S5: Use a genetic algorithm to solve the power system planning model and obtain the optimal power system planning scheme, including the output ratio of the generator sets, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment.

2. The method for power system planning for renewable energy according to claim 1, characterized in that: In the step S2, specifically, Cleaning the historical renewable resource power generation, the historical meteorological data, and the predicted meteorological data, including processing missing values, outliers, and noise data; Normalizing or standardizing the historical meteorological data and the predicted meteorological data; Aligning the historical renewable resource power generation, the historical meteorological data, and the predicted meteorological data in time series to form a unified data set; Extract key features from historical and forecasted meteorological data, including wind direction, wind speed, and solar radiation; Train a random forest model based on key features of historical meteorological data and historical renewable energy generation power; The pre-processed forecasted meteorological data is input into the random forest model to predict the renewable energy power generation in a preset time period.

3. The method for power system planning for renewable energy according to claim 1, characterized in that: In the step S3, specifically, Clean and normalize the load data and historical load data collected in step S1, remove outliers and missing values, and normalize the data to the same scale; Extract features from the preprocessed data, including time features and historical load features; Constructing an LSTM neural network model, wherein the LSTM neural network model includes an input layer, a hidden layer, and an output layer, wherein the hidden layer is composed of multiple LSTM units; Use historical load data to train the LSTM neural network model, optimize the LSTM neural network model parameters through the back propagation algorithm, and minimize the prediction error; The LSTM neural network model trained with real-time collected load data is used to predict the power load demand within a preset future time range.

4. The method for power system planning for renewable energy according to claim 1, characterized in that: In the step S4, specifically, Defining decision variables of the power system planning model, wherein the decision variables include the output of the generator set, the charge and discharge power of the energy storage system, and the utilization rate of the renewable energy power generation equipment; Presetting an optimization goal, wherein the optimization goal includes minimizing power generation cost and maximizing renewable energy utilization; Preset constraints, wherein the constraints include power balance constraints, grid security constraints, and energy storage system constraints; The predicted power generation power, predicted power load demand, optimization objectives and constraints are integrated to construct a power system planning model.

5. The method for power system planning for renewable energy according to claim 1, characterized in that: The step S5 specifically includes the following sub-steps: S51: Convert the power system planning model into an optimization problem, and define an objective function and constraints. The objective function includes minimizing power generation cost and maximizing renewable energy utilization. The constraints include power balance constraints, grid security constraints, and energy storage system constraints. S52: Initializing a population of a genetic algorithm, where the population consists of a plurality of individuals, each of which represents a possible power system planning scheme, including the output ratio of the generator sets, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment; S53: Calculating the fitness value of each individual in the population, where the fitness value is calculated according to the objective function; S54: Generate a new generation population through selection, crossover and mutation operations, wherein the selection operation selects excellent individuals based on fitness values, the crossover operation generates new individuals by exchanging individual genes, and the mutation operation introduces diversity by randomly changing individual genes; S55: Repeat the sub-steps S53 and S54 until a preset number of iterations is reached; S56: Select the individual with the best fitness value from the final population as the optimal power system planning scheme, including the output ratio of the generator sets, the charging and discharging strategy of the energy storage system, and the output ratio of renewable energy power generation equipment; S57: Verify the optimal power system planning scheme to see whether it meets preset constraints. If so, output the optimal power system planning scheme.

Images